Qwen3.5-28B-A3B-REAP benchmark on an M4 Pro · 64 GB

{
  "runId": "run_7c4e5752-d369-448e-85b1-8099f399f340",
  "bundleId": "llamacpp-qwen-3.5-28b-a3b-reap-q4_k_m.gguf-331251",
  "status": "verified",
  "promptTokens": 40960,
  "completionTokens": 10240,
  "contextLength": 5120,
  "harness": {
    "version": "0.1.18",
    "gitSha": "unknown"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "b8793",
    "buildFlags": "metal"
  },
  "model": {
    "displayName": "Qwen3.5-28B-A3B-REAP",
    "format": "gguf",
    "quant": "q4_k_m",
    "architecture": "qwen35moe",
    "source": null,
    "fileSizeBytes": 17264580864,
    "lab": {
      "name": "0xSero",
      "slug": "0xsero"
    },
    "quantizedBy": null
  },
  "device": {
    "cpu": "Apple M4 Pro",
    "cpuCores": 14,
    "gpu": "Apple M4 Pro",
    "gpuCores": 20,
    "gpuCount": 1,
    "ramGb": 64,
    "osName": "macOS",
    "osVersion": "26.3"
  },
  "decodeTpsMean": 50.5,
  "prefillTpsMean": 752.1,
  "ttftP50Ms": 5448.81,
  "idleTpsMean": 16259.6,
  "peakRssMb": 16285.6,
  "trialsPassed": 10,
  "trialsTotal": 10,
  "runnabilityScore": 0.6944606277901786,
  "bundleSha256": "f96d6bf48ab6f56ccd7165ab3464793e631aa1e64d91d4e7cf6033073d467356",
  "createdAt": "2026-04-04T05:56:46.961Z"
}